Feature selection (FS) is one of the major tasks in data cleansing step in machine learning. However, multi-objective FS is more challenging because it tries to optimize two conflicting objectives, namely minimizing the feature set and classification error. In this way, evolutionary algorithms are promising solutions aimed to obtain more reliable Pareto fronts. However, unfortunately they suffer from consuming much time due to exploration in a large search space. Another issue encountered in multi-objective FS approaches is related to the correlation between features. This challenge arises because choosing such features reduces the performance of the classification. To address these challenges, we introduce a multi-objective FS approach that makes several significant contributions. First, the proposed method deals with the correlation between features through a novel probability structure. Secondly, it relies on the Pareto Archived Evolution Strategy (PAES) method, which offers many advantages, including simplicity and its ability to explore the solution space at an acceptable speed. We enhance the PAES structure in a manner that promotes the intelligent generation of offsprings. Consequently, our proposed approach benefits from the introduced probability structure to generate more promising offspring. Lastly, it incorporates a novel strategy to guide the algorithm to find the optimal subset throughout the evolutionary process. The obtained results on real-world datasets reveal a substantial enhancement in the quality of the final solutions.
原文链接
分享
引用
